---
title: "Set Up Agent Skills for DGX Station — Overview"
canonical: "https://build.nvidia.com/playbooks/dgx-station-ai-skills/overview.md"
---

# Basic idea

This playbook installs four native Agent Skills plus a dependency-free `dgx-assist` command-line tool into a project you choose. Asking your AI coding agent to serve a model or explain why a GPU is unavailable produces answers grounded in your actual hardware instead of recalled generic advice.

The skills route the agent through a fixed workflow: inspect the real hardware, search a pinned snapshot of NVIDIA guidance, resolve an exact named model to a qualified recipe, run preflight, ask you to approve, then act and verify. Every mutation requires your confirmation, and `dgx-assist` only ever stops services it started and labelled as its own.

The same CLI works without an agent. Add `--json` and it emits a stable versioned envelope for scripts and CI; omit it and you get readable headings, tables, and action previews for terminal use.

# What you'll accomplish

You'll install the four skills and the `dgx-assist` CLI into a project, then drive a qualified vLLM inference workload from a plain-language request through preflight, approval, launch, and verification on your **hardware platform**.

You'll also be able to:

- Inspect your software profile and see exactly which actions its release qualifies it for
- Search pinned NVIDIA Development Guide and Bring-Up Guide content with revision and source-digest provenance on every result
- Plan MIG layouts and run read-only diagnostics that produce redacted support bundles

# What to know before starting

**Required:**

- Experience with the Linux command line and running shell scripts
- Familiarity with an AI coding agent — Claude Code, Codex, Gemini CLI, or Cursor — and how it loads project-level context
- Basic understanding of Docker containers and GPU device selection

**Optional:**

- Familiarity with vLLM or SGLang inference serving

Two safety rules matter more than the rest, and the skills enforce them for you: select GPUs by UUID rather than by `nvidia-smi` index, which is not a CUDA ordinal on this hardware platform; and treat an unrecognized software build as unknown rather than assuming it behaves like a qualified one.

# Supported hardware platforms

Use the matrix below to confirm your hardware platform, recommended default local settings, and whether multi-node applies.

| Hardware platform | OS | Memory | Recommended default local settings | Multi-node capable hardware |
| :---- | :---- | :---- | :---- | :---- |
| **DGX Station** | DGX OS (Linux) | Large HBM + Grace DRAM | Four Agent Skills + `dgx-assist`; GB300 compute capability `10.3`; smoke recipe `Qwen/Qwen2.5-Coder-1.5B-Instruct` on vLLM | — |

# Prerequisites

**Hardware requirements**

- Supported hardware platform — see Supported hardware platforms matrix above
- GB300 compute capability `10.3`, confirmed by `nvidia-smi --query-gpu=compute_cap --format=csv`
- At least 20 GB available storage for the qualified model weights and container image

**Software requirements**

- Python 3.11 or newer: `python3 --version`
- Docker with the NVIDIA Container Toolkit: `docker info | grep -i runtime`
- One supported AI coding agent installed: `claude --version`, `codex --version`, `gemini --version`, or Cursor
- Network access to download model weights and container images on first run
- No inbound port access is required; inference binds to localhost by default

# Ancillary files

All required assets can be found [in the playbook repository](https://github.com/NVIDIA/dgx-spark-playbooks/blob/main/nvidia/playbook-dgx-station-ai-skills/).

- `assets/install.sh` — Thin wrapper that runs the Python installer
- `assets/installer.py` — Installs, updates, migrates, and uninstalls the skills; writes `.dgx-station/install-manifest.json` and manages the delimited NVIDIA block in your agent context file
- `assets/dgx-assist.pyz` — The standalone zipapp CLI providing host inspection, guidance search, recipe resolution, preflight, service lifecycle, MIG planning, and diagnostics
- `assets/skills/dgx-station/` — Platform compatibility, coherency, GPU selection, container, CDI, and power guidance
- `assets/skills/dgx-station-inference/` — Exact-model recipe resolution, preflight, approved launch, verification, and owned service lifecycle
- `assets/skills/dgx-station-mig/` — Driver-discovered MIG inspection, planning, approved apply, and restoration evidence
- `assets/skills/dgx-station-diagnose/` — Read-only diagnostics, playbook correlation, redacted bundles, and one allowlisted fix at a time
- `assets/AGENTS.md` — The managed context block written into your agent's project context file

# Time & risk

- **Estimated time:** 15 MIN to install and verify, plus 20–40 minutes if you run the qualified inference recipe (most of that is the first model and container download)
- **Risk level:** Low
- The installer refuses unmanaged file collisions and symlink destinations rather than overwriting anything it does not own
- First-run model and container downloads require network bandwidth and may fail on a slow or interrupted connection
- Only one model is qualified to launch in v1; larger bundled candidates are reported as non-runnable by design
- MIG changes are disruptive and are blocked unless your release profile enables them and you explicitly approve the plan
- **Rollback:** Run `assets/install.sh uninstall --target /path/to/project` to remove every manifest-owned file and the delimited context block. The installer preserves any managed file you modified and leaves unrelated context untouched. A user-scope CLI installed with `install-cli` is removed by deleting `~/.local/bin/dgx-assist`. Cached state lives under `~/.cache/dgx-assist/` and `~/.local/state/dgx-assist/` and can be deleted.
- **Last Updated:** 10/21/2026
- `dgx-assist` now recognizes a WSL2 guest and reports `Compatibility: WSL2` with read-only diagnostics instead of an untrusted release marker
- Install Agent Skills and `dgx-assist`, inspect the release profile, search pinned guidance, and run the qualified vLLM smoke recipe with approval on supported hardware platforms